© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 2-GEMMASCOPE-RES-16K
    11. 7084
    Prev
    Next
    INDEX
    Explanations

    occurrences of specific variable or parameter designations in mathematical or programming contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    IntoConstraints
    -0.44
    AutoScaleMode
    -0.43
     Whittaker
    -0.39
    ủ
    -0.37
    uber
    -0.36
    يميديا
    -0.36
    CBM
    -0.36
     Whit
    -0.35
    bring
    -0.34
    swig
    -0.34
    POSITIVE LOGITS
    q
    2.02
     q
    1.95
     Q
    1.81
    Q
    1.69
    qa
    1.49
    iq
    1.43
    qs
    1.41
    aq
    1.39
    cq
    1.39
    Ｑ
    1.38
    Activations Density 0.327%

    No Known Activations